AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA

SUBMITTED BY:

AJMAL N K

LIJU JOHN

MUHAMMED SAHAL C

NABEELA PARVEEN K

RAJASREE PUSHPAN

1

INTRODUCTIONAutomatic License Plate Recognition (ALPR) system is an important technique, used in Intelligent Transportation System.

ALPR is used for automatic vehicle identification.

Intelligent Transportation System (ITS) provides the data of vehicle numbers which can be used in follow up, analyses and monitoring.

It is an image processing technology used to identify vehicles by only their license plates.

Applications:

Traffic problems, highway toll collection, borders and custom security, premises where high security is needed, like Parliament, Legislative Assembly, and so on.

2

MOTIVATION For the standard number plate, ALPR system is easier to read and recognize.

In India this task becomes much difficult due to variation in plate model and their size.

Character recognition part is also very difficult in Indian number plate.

So flexible algorithm required for solved this task.

Use of vehicles has been increasing because of population growth and human needs in recent years.

Therefore, control of vehicles is becoming a big problem and much more difficult to solve.

License Plate Recognition systems are used for the purpose of effective control.

3

EXISTING SYSTEMLPRs is done with the help of filter like morphological filter.

Image dilation and eroding helps to find the text in License plate .

30% of the large agencies that don’t have LPR.

The primary use of LPR systems they intended for to detect and reduce auto theft.

It appears the greatest concerns center on costs and mechanical maintenance problems.

Only Character Structure can be analysed.

4

PROPOSED SYSTEMThe ALPR using VEDA is generally framed into the steps:

1. Number plate extraction

2. Character segmentation

3. Character recognition

Images are taken out with different illumination conditions, different background and orientation.

Histogram equalization, median filter are used which take care of lighting and contrast problem.

Sobel vertical edge detection.

Morphology is employed to locate the number plate.

Projection analysis is used to segment the characters present on the plate.

For recognition work template is used.

5

Flow chart of ALPR

6

NUMBER PLATE EXTRACTION Key step in ALPR system & influences the accuracy of the system.

Extraction of number plate is difficult task, due to:

* Number plates generally occupy a small portion of whole image.

* Difference in number plate formats

* Influence of environmental factors.

This step affects the accuracy of character segmentation and recognition work.

The goal of this phase, given an input image, is to produce a number of candidate regions, with high probability of containing number plate and validate for true number plate.

7

Image Acquisition & pre-processing

High resolution digital camera is used to acquire an image.

Images are taken in different background, illumination conditions, and at various distances from the camera to vehicle.

Image converted RGB to gray scale all the processing steps are executed on gray scale image.

Grey Scale Image

Pre-processing is used to enhance the processing speed, improve the contrast of image & to reduce the noise in the image.

8

Morphological OperationMorphological opening operation used using structure element on vehicle gray scale image then subtracted from original image.

Thus number plate and other parts like lights are stay in new image and unwanted parts remove from image.

Effect of Opening operation using disk

9

show subtraction between two images.

Grey scale image - opened image

10

Thresholding Operation Threshold operation is converted gray scale image into binary image by calculating level of threshold.

First find minimum and maximum value of pixel from image.

This operation converted all pixels in 0-1 form and makes further processing simple.

Thresholding Image

11

Vertical Edge detection The characters on number plate region contain abundant edges as compared to background area.

This feature is employed for locating the candidate plate area from the input image.

Sobel vertical edge detection is used to find out the regions.

Sobel Vertical Edge Detection

12

Candidate Plate Area DetectionMorphological operations aim to remove unrelated objects in the image.

Closing and opening are used to extract candidate plate areas from the entire image.

Sometimes background areas may also get declared as candidate plate.

To remove the fake candidates, plate validation is done using the aspect ratio of the plate and horizontal cuts in the number plate.

Plate area detection image

13

True Number Plate Extraction Bounding Box analysis is used to extract plate area from the original image.

From the Bounding Box analysis, respective row and column indices of plate area are found out.

Once the indices of number plate are known, the number plate is extracted from original gray scale image.

Extracted True Number Plate

14

Adjust Number Plate appropriate angle

This operation is used when number plate is not in horizontal position.

Rotation of number plate is required for true recognition.

Extracted Plate & Rotated Plate

15

CHARACTER SEGMENTATIONCharacter isolation from the number plate region is the important step in ALPR system.

Which influences the accuracy of character recognition significantly.

The goal of this phase, given the number plate image, is to segment all the characters, without losing features of the characters.

16

Character Region Enhancement

First converted true number plate image into binary image by using gray thresh (image) function. Erosion operation is used for focusing each character.

Here characters are in black colour so erosion made characters thick.

Binarized Number Plate Erode Image

17

Connected Component AnalysisTo remove the noise, other than characters on the plate.

Each labelled matrix of 8-connectivity pixels is evaluated based on the area threshold.

Converted Black to White Connected Component Analysis

18

Vertical Projection AnalysisCharacter segmentation is implemented to isolate each character on the number plate.

Vertical projection analysis is used to find the gaps between the characters.

The characters are segmented based on the number of valleys in projection.

Row and column indices of each character are recorded, and it is extracted from the original gray scale number plate.

Isolates every letter and digit on the number plate oriented horizontally in one row, along the width of number plate

19

Segmented Character Image

20

CHARACTER RECOGNITION

Template Matching

1) Loading template

This operation loads a template of character.

Take 24 X 42 pixel A to Z alphabet and 0 to 9 number images.

Read this all image and store in database. It becomes 36 character templates.

2)Character Normalization

Segmented characters have very much variation in size.

All the characters are normalized to predefined height (Vertical Length) in pixel. As the characters always have variable width (Horizontal Length).

Each character image is normalized to a size of 24 X 42, by image mapping technique.

21

3)Template matching

Normalized character image compare with each template character image and find correlation between segmented character and template character.

Selecting the most relevant image and write into text file.

Feature based character Recognition

Feature Extraction serves two purposes;

one is to extract properties that can identify a character uniquely.

Second is to extract properties that can differentiate between similar characters

A character can be written in a variety of ways.

There exist a set of principles or logics that surpass all variation differences.

22

ADVANTAGESAnalysing texture in unlimited orientation and scales.

Detecting straight lines with upto 30 inclination.

ALPR does depend in colour, font, language, background images of the number plate.

The experiment can be conducted in variety of environments.

High definition plate image processing and ambiguous character recognition.

23

SCREEN SHOTS

Home Page Upload Number Plate

24

Select Image Uploaded Image

25

Grey Scale Image Erosion

26

Dilation Subtraction

27

Recognized Number

28

EXPERIMENTAL RESULTSA database consists of different sized JPEG colored images.

Total 150 images are used to test the algorithm.

The images are taken with different background as well as illumination conditions.

Experiments show that the algorithm has good performance on number plate extraction, and character segmentation work. It can deal the images correctly, with noise, illumination variance, and rotation to ±50.

This work also using jar files to implement.

Deep shadows and reflections have an impact on number plate extraction work. Because of uneven illumination, stained number plates, true number plates could not get correctly extracted.

29

CONCLUSIONThe proposed method is mainly designed for real time License Plate.

Using web camera is for monitoring images and also low resolution images are used.

New and fast algorithm which is useful for real time requirement.

Computation time is of 47.7ms with an efficiency of 91.4%.

30